3 papers
cs.LG2026
On the Dynamics & Transferability of Latent Generalization during Memorization
Simran Ketha, Venkatakrishnan Ramaswamy
Deep networks have been known to have extraordinary generalization abilities, via mechanisms that aren't yet well understood. It is also known that upon shuffling labels in the tra…
cs.LG2026
Decoding Generalization from Memorization in Deep Neural Networks
Simran Ketha, Venkatakrishnan Ramaswamy
Overparameterized deep networks that generalize well have been key to the dramatic success of deep learning in recent years. The reasons for their remarkable ability to generalize…
cs.CV2024
Peter Parker or Spiderman? Disambiguating Multiple Class Labels
Nuthan Mummani, Simran Ketha, Venkatakrishnan Ramaswamy
In the supervised classification setting, during inference, deep networks typically make multiple predictions. For a pair of such predictions (that are in the top-k predictions), t…